Skip to content
Snippets Groups Projects
Commit fb176462 authored by Sören Henning's avatar Sören Henning
Browse files

Work on scalability graphs

parent 3f6da3a1
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
execution/scalability-graph-finish.ipynb 0 → 100644
+ 106
− 0
View file @ fb176462
%% Cell type:code id: tags:
```
import os
import requests
from datetime import datetime, timedelta, timezone
import pandas as pd
import matplotlib.pyplot as plt
```
%% Cell type:code id: tags:
```
exp_id = 1025
warmup_sec = 60
warmup_partitions_sec = 120
threshold = 2000 #slope
directory = '../results-inst'
```
%% Cell type:code id: tags:
```
df1 = pd.read_csv(os.path.join(directory, 'exp1025_min-suitable-instances.csv')).set_index('dim_value').rename(columns={"instances": "1025"})
df2 = pd.read_csv(os.path.join(directory, 'exp1003_min-suitable-instances.csv')).set_index('dim_value').rename(columns={"instances": "1003"})
#df1.join(df2, on='instances')
df = df1.join(df2, how='outer')
df
```
%% Cell type:code id: tags:
```
plt.style.use('ggplot')
plt.rcParams['axes.facecolor']='w'
plt.rcParams['axes.edgecolor']='555555'
#plt.rcParams['ytick.color']='black'
plt.rcParams['grid.color']='dddddd'
plt.rcParams['axes.spines.top']='false'
plt.rcParams['axes.spines.right']='false'
plt.rcParams['legend.frameon']='true'
plt.rcParams['legend.framealpha']='1'
plt.rcParams['legend.edgecolor']='1'
plt.rcParams['legend.borderpad']='1'
plt.figure()
ax = df.plot(kind='line', marker='o')
#ax = df.plot(kind='line',x='dim_value', legend=False, use_index=True)
ax.set_ylabel('instances')
ax.set_xlabel('data sources')
ax.set_ylim(ymin=0)
#ax.set_xlim(xmin=0)
```
%% Cell type:code id: tags:
```
```
execution/scalability-graph.ipynb
+ 11
− 2
View file @ fb176462
%% Cell type:code id: tags:
```
print("hello")
```
%% Cell type:code id: tags:
```
import os
import requests
from datetime import datetime, timedelta, timezone
import pandas as pd
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
```
%% Cell type:code id: tags:
```
os.getcwd()
```
%% Cell type:code id: tags:
```
exp_id = 1009
exp_id = 1003
warmup_sec = 60
warmup_partitions_sec = 120
threshold = 2000 #slope
directory = './results-final'
directory = '../results'
```
%% Cell type:code id: tags:outputPrepend,outputPrepend
```
#exp_id = 35
#os.chdir("./results-final")
raw_runs = []
filenames = [filename for filename in os.listdir(directory) if filename.startswith(f"exp{exp_id}") and filename.endswith("totallag.csv")]
for filename in filenames:
#print(filename)
run_params = filename[:-4].split("_")
dim_value = run_params[2]
instances = run_params[3]
df = pd.read_csv(os.path.join(directory, filename))
#input = df.loc[df['topic'] == "input"]
input = df
#print(input)
input['sec_start'] = input.loc[0:, 'timestamp'] - input.iloc[0]['timestamp']
#print(input)
#print(input.iloc[0, 'timestamp'])
regress = input.loc[input['sec_start'] >= warmup_sec] # Warm-Up
#regress = input
#input.plot(kind='line',x='timestamp',y='value',color='red')
#plt.show()
X = regress.iloc[:, 2].values.reshape(-1, 1) # values converts it into a numpy array
Y = regress.iloc[:, 3].values.reshape(-1, 1) # -1 means that calculate the dimension of rows, but have 1 column
linear_regressor = LinearRegression() # create object for the class
linear_regressor.fit(X, Y) # perform linear regression
Y_pred = linear_regressor.predict(X) # make predictions
trend_slope = linear_regressor.coef_[0][0]
#print(linear_regressor.coef_)
row = {'dim_value': int(dim_value), 'instances': int(instances), 'trend_slope': trend_slope}
#print(row)
raw_runs.append(row)
lags = pd.DataFrame(raw_runs)
```
%% Cell type:code id: tags:
```
lags.head()
```
%% Cell type:code id: tags:
```
raw_partitions = []
filenames = [filename for filename in os.listdir(directory) if filename.startswith(f"exp{exp_id}") and filename.endswith("partitions.csv")]
for filename in filenames:
#print(filename)
run_params = filename[:-4].split("_")
dim_value = run_params[2]
instances = run_params[3]
df = pd.read_csv(os.path.join(directory, filename))
#input = df.loc[df['topic'] == "input"]
input = df
#print(input)
input['sec_start'] = input.loc[0:, 'timestamp'] - input.iloc[0]['timestamp']
#print(input)
#print(input.iloc[0, 'timestamp'])
input = input.loc[input['sec_start'] >= warmup_sec] # Warm-Up
#regress = input
input = input.loc[input['topic'] >= 'input']
mean = input['value'].mean()
#input.plot(kind='line',x='timestamp',y='value',color='red')
#plt.show()
row = {'dim_value': int(dim_value), 'instances': int(instances), 'partitions': mean}
#print(row)
raw_partitions.append(row)
partitions = pd.DataFrame(raw_partitions)
#runs = lags.join(partitions.set_index(['dim_value', 'instances']), on=['dim_value', 'instances'])
```
%% Cell type:code id: tags:
```
raw_obs_instances = []
filenames = [filename for filename in os.listdir(directory) if filename.startswith(f"exp{exp_id}") and filename.endswith("instances.csv")]
for filename in filenames:
run_params = filename[:-4].split("_")
dim_value = run_params[2]
instances = run_params[3]
df = pd.read_csv(os.path.join(directory, filename))
if df.empty:
continue
#input = df.loc[df['topic'] == "input"]
input = df
#print(input)
input['sec_start'] = input.loc[0:, 'timestamp'] - input.iloc[0]['timestamp']
#print(input)
#print(input.iloc[0, 'timestamp'])
input = input.loc[input['sec_start'] >= warmup_sec] # Warm-Up
#regress = input
#input = input.loc[input['topic'] >= 'input']
#mean = input['value'].mean()
#input.plot(kind='line',x='timestamp',y='value',color='red')
#plt.show()
#row = {'dim_value': int(dim_value), 'instances': int(instances), 'obs_instances': mean}
#print(row)
raw_obs_instances.append(row)
obs_instances = pd.DataFrame(raw_obs_instances)
obs_instances.head()
```
%% Cell type:code id: tags:
```
runs = lags
#runs = lags.join(partitions.set_index(['dim_value', 'instances']), on=['dim_value', 'instances'])#.join(obs_instances.set_index(['dim_value', 'instances']), on=['dim_value', 'instances'])
#runs["failed"] = runs.apply(lambda row: (abs(row['instances'] - row['obs_instances']) / row['instances']) > 0.1, axis=1)
#runs.loc[runs['failed']==True]
```
%% Cell type:code id: tags:
```
#threshold = 1000
# Set to true if the trend line has a slope less than
runs["suitable"] = runs.apply(lambda row: row['trend_slope'] < threshold, axis=1)
runs.columns = runs.columns.str.strip()
runs.sort_values(by=["dim_value", "instances"])
```
%% Cell type:code id: tags:
```
filtered = runs[runs.apply(lambda x: x['suitable'], axis=1)]
grouped = filtered.groupby(['dim_value'])['instances'].min()
min_suitable_instances = grouped.to_frame().reset_index()
min_suitable_instances
```
%% Cell type:code id: tags:
```
min_suitable_instances.to_csv(f'../results-inst/exp{exp_id}_min-suitable-instances.csv', index=False)
```
%% Cell type:code id: tags:
```
min_suitable_instances.plot(kind='line',x='dim_value',y='instances')
# min_suitable_instances.plot(kind='line',x='dim_value',y='instances', logy=True)
plt.show()
```
%% Cell type:code id: tags:
```
```
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment